network analytics
Recently Published Documents


TOTAL DOCUMENTS

161
(FIVE YEARS 67)

H-INDEX

13
(FIVE YEARS 3)

PLoS ONE ◽  
2022 ◽  
Vol 17 (1) ◽  
pp. e0261947
Author(s):  
Sharon Hassin-Baer ◽  
Oren S. Cohen ◽  
Simon Israeli-Korn ◽  
Gilad Yahalom ◽  
Sandra Benizri ◽  
...  

Objective The purpose of this study is to explore the possibility of developing a biomarker that can discriminate early-stage Parkinson’s disease from healthy brain function using electroencephalography (EEG) event-related potentials (ERPs) in combination with Brain Network Analytics (BNA) technology and machine learning (ML) algorithms. Background Currently, diagnosis of PD depends mainly on motor signs and symptoms. However, there is need for biomarkers that detect PD at an earlier stage to allow intervention and monitoring of potential disease-modifying therapies. Cognitive impairment may appear before motor symptoms, and it tends to worsen with disease progression. While ERPs obtained during cognitive tasks performance represent processing stages of cognitive brain functions, they have not yet been established as sensitive or specific markers for early-stage PD. Methods Nineteen PD patients (disease duration of ≤2 years) and 30 healthy controls (HC) underwent EEG recording while performing visual Go/No-Go and auditory Oddball cognitive tasks. ERPs were analyzed by the BNA technology, and a ML algorithm identified a combination of features that distinguish early PD from HC. We used a logistic regression classifier with a 10-fold cross-validation. Results The ML algorithm identified a neuromarker comprising 15 BNA features that discriminated early PD patients from HC. The area-under-the-curve of the receiver-operating characteristic curve was 0.79. Sensitivity and specificity were 0.74 and 0.73, respectively. The five most important features could be classified into three cognitive functions: early sensory processing (P50 amplitude, N100 latency), filtering of information (P200 amplitude and topographic similarity), and response-locked activity (P-200 topographic similarity preceding the motor response in the visual Go/No-Go task). Conclusions This pilot study found that BNA can identify patients with early PD using an advanced analysis of ERPs. These results need to be validated in a larger PD patient sample and assessed for people with premotor phase of PD.


2021 ◽  
pp. 109861112110572
Author(s):  
Timothy I. C. Cubitt

Research into police misconduct traditionally considers the correlates and antecedents of misconduct among individual officers, as a means of disruption or prevention. However, more recently, deviance among police has been considered through network perspectives. This study considered 7755 allegations of misconduct accrued by 1495 officers from the Baltimore Police Department between January 2015 to January 2020. A social network analysis was employed to consider the characteristics and differences of misconduct networks between assignments and to identify key officers within these networks. Findings suggested that the misconduct networks of patrol assignments functioned marginally different to investigations or specialist duties. Discrete communities of misconduct were identified within each assignment, including a small number of officers that were particularly important to supporting these networks. This study holds practical implications for the identification and disruption of misconduct networks among law enforcement agencies.


2021 ◽  
Vol 9 (4) ◽  
pp. 56
Author(s):  
Shardul Shankar ◽  
Vijayshri Tewari

Social networks have created an information diffusion corpus that provides users with an environment where they can express their views, form a community, and discuss topics of similar or dissimilar interests. Even though there has been an increasingly rising demand for conducting an emotional analysis of the users on social media platforms, the field of emotional intelligence (EI) has been rather slow in exploiting the enormous potential that social media can play in the research and practice of the framework. This study, thus, tried to examine the role that the microblogging platform Twitter plays in enhancing the understanding of the EI community by building on the Twitter Analytics framework of Natural Language Processing to further develop the insights of EI research and practice. An analysis was conducted on 53,361 tweets extracted using the hashtag emotional intelligence through descriptive analytics (DA), content analytics (CA), and network analytics (NA). The findings indicated that emotional intelligence tweets are used mostly by speakers, psychologists (or other medical professionals), and business organizations, among others. They use it for information dissemination, communication with stakeholders, and hiring. These tweets carry strong positive sentiments and sparse connectedness. The findings present insights into the use of social media for understanding emotional intelligence.


2021 ◽  
Vol 15 (4) ◽  
pp. 101202
Author(s):  
Yi Zhang ◽  
Mengjia Wu ◽  
Wen Miao ◽  
Lu Huang ◽  
Jie Lu

Author(s):  
Alex M. R. Ruelas ◽  
Christian E. Rothenberg

The growth of cloud application services delivered through data centers with varying traffic demands unveils limitations of traditional load balancing methods. Aiming to attend evolving scenarios and improve the overall network performance, this paper proposes a load balancing method based on an Artificial Neural Network (ANN) in the context of Knowledge-Defined Networking (KDN). KDN seeks to leverage Artificial Intelligence (AI) techniques for the control and operation of computer networks. KDN extends Software-Defined Networking (SDN) with advanced telemetry and network analytics introducing a so-called Knowledge Plane. The ANN is capable of predicting the network performance according to traffic parameters paths. The method includes training the ANN model to choose the path with least load. The experimental results show that the performance of the KDN-based data center has been greatly improved.


2021 ◽  
Author(s):  
Lu Huang ◽  
Xiang Chen ◽  
Yi Zhang ◽  
Yihe Zhu ◽  
Suyi Li ◽  
...  

2021 ◽  
Vol 39 (28_suppl) ◽  
pp. 211-211
Author(s):  
Stephanie Broadnax Broussard ◽  
John Russell Hoverman ◽  
Lalan S. Wilfong ◽  
Sabrina Q. Mikan ◽  
Holly Books ◽  
...  

211 Background: Improving the quality of End of Life (EOL) care continues to be a challenge. Enhanced prognostic awareness is critical for all members of the clinical team. In December 2020, The McKesson Advance Care Planning Enrollment eXtended (APEX) mortality risk predictive analytics model was implemented to improve prognostic awareness in OCM population and improve the timing of initiation of end of life care. (See ASCO 2021 abstract #1560). Methods: The APEX tool was provided in collaboration with the McKesson/US Oncology network analytics team. A process was established for dissemination of the report information. In the pilot, 12 practice locations with varying community landscapes, socio-cultural dynamics, and site clinical personnel resources were selected. At each site clinical leads and physician champions were selected. Education was provided on the tool, prognostic variables, and appropriate interventions. Biweekly, each site was provided a list of stratified patients based on their risk of mortality within the next 90 days. Patients that were identified as “very high” or “high” risk were reviewed by the clinical teams and discussed in routine huddles. Physicians and teams reported their planned interventions before and after mortality risk identification. Results: In the pilot, 105 patients were identified as very high or high risk. Reported interventions included the option to continue treatment, ACP Discussion, hospice referral/enrollment, palliative care referral, or continue close monitoring. Prior to the report, 14 identified patients were admitted to hospice and 30 patients had 1 or more advance directives documented. For 26 patients, treatment changes occurred including hospice enrollment, reduction in chemotherapy dosage, change in regimen, or initiating intensive monitoring. 23 patients indicated on the report expired in the interim between generation of the report and receipt by the clinic. No changes in treatment were made in 22 patients. There was physician reported disagreement with the mortality risk assessment in 4 patients. Conclusions: We describe implementation of a mortality predictive model in our practice. The care teams found the tool useful to identify patients at high risk of mortality. Interventions were varied and we will track the outcomes based on intervention. We are using the information from the pilot to continue refining the tool and implementation.


2021 ◽  
Author(s):  
Lorin M Towle-Miller ◽  
Jeffrey C Miecznikowski

Advancements in genomic sequencing continually improve personalized medicine in complex diseases. Recent breakthroughs generate multiple types of signatures (or multi-omics) from each cell, producing different data 'omic' types per single-cell experiment. We introduce MOSCATO, a technique for selecting features across multi-omic single-cell datasets that relate to clinical outcomes. For example, we leverage penalization concepts often used in multi-omic network analytics to accommodate the high-dimensionality where multiple-testing is likely underpowered. We organize the data into multi-dimensional tensors where the dimensions correspond to the different 'omic' types. Using the outcome and the single-cell tensors, we perform regularized tensor regression to return a variable set for each 'omic' type that forms the clinically-associated network. Robustness is assessed over simulations based on available single-cell simulation methods. Real data comparing healthy subjects versus subjects with leukemia is also considered in order to identify genes associated with the disease. The flexibility of our approach enables future extensions on distributional assumptions and covariate adjustments. This algorithm may identify clinically-relevant genetic patterns on a cellular-level that span multiple layers of sequencing data and ultimately inform highly precise therapeutic targets in complex diseases. Code to perform MOSCATO and replicate the real data application is publicly available on GitHub at https://github.com/lorinmil/MOSCATO and https://github.com/lorinmil/MOSCATOLeukemiaExample.


Author(s):  
Subrata Saha ◽  
Ahmed Soliman ◽  
Sanguthevar Rajasekaran

Sign in / Sign up

Export Citation Format

Share Document